CN110376963A - It is a kind of based on the closed-loop control precision machining method detected in place and system - Google Patents

It is a kind of based on the closed-loop control precision machining method detected in place and system Download PDF

Info

Publication number
CN110376963A
CN110376963A CN201910646784.8A CN201910646784A CN110376963A CN 110376963 A CN110376963 A CN 110376963A CN 201910646784 A CN201910646784 A CN 201910646784A CN 110376963 A CN110376963 A CN 110376963A
Authority
CN
China
Prior art keywords
workpiece
key point
loop control
closed
error
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201910646784.8A
Other languages
Chinese (zh)
Other versions
CN110376963B (en
Inventor
张云
刘家欢
黄志高
周华民
李德群
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan moding Technology Co.,Ltd.
Original Assignee
Huazhong University of Science and Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Huazhong University of Science and Technology filed Critical Huazhong University of Science and Technology
Priority to CN201910646784.8A priority Critical patent/CN110376963B/en
Publication of CN110376963A publication Critical patent/CN110376963A/en
Application granted granted Critical
Publication of CN110376963B publication Critical patent/CN110376963B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00Programme-control systems
    • G05B19/02Programme-control systems electric
    • G05B19/18Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
    • G05B19/401Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by control arrangements for measuring, e.g. calibration and initialisation, measuring workpiece for machining purposes
    • G05B19/4015Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by control arrangements for measuring, e.g. calibration and initialisation, measuring workpiece for machining purposes going to a reference at the beginning of machine cycle, e.g. for calibration
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00Program-control systems
    • G05B2219/30Nc systems
    • G05B2219/34Director, elements to supervisory
    • G05B2219/34242For measurement only

Landscapes

  • Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Manufacturing & Machinery (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Numerical Control (AREA)

Abstract

The invention discloses a kind of based on the closed-loop control precision machining method detected in place and system, belongs to precision machinery manufacture field.This method comprises: S1, machine tool carry out time processing process according to machining path is preset;S2, the outer dimension of in-situ acquisition workpiece, profile critical spot size and machined parameters, and neural network intelligent compensation model is inputted in real time, it calculates the error compensation value C of cutter and optimizes the machining path of next step accordingly, dynamic in real time is carried out with the processing to next step and is compensated;S3, it regard the machining path of the next step after step S2 optimization as the default machining path of step S1, repeats step S1, S2 up to completing the process.The present invention obtains the local critical size in process by on-position measure in real time, it calculates mismachining tolerance and processing offset is calculated based on neural network algorithm real-time fitting, Automatic Optimal machining path realizes the Precision Machining of real-time closed-loop control to reduce mismachining tolerance.

Description

It is a kind of based on the closed-loop control precision machining method detected in place and system
Technical field
The invention belongs to precision machinery manufacture fields, more particularly, to a kind of closing in real time based on detection technique in place Ring controls precision parts system of processing and method.
Background technique
With the development of machining manufacturing technology, component of machine production requirement is higher and higher, such as manufactures in mold It is intended to complication and precise treatment with fields, the physique structure processing of workpiece such as lithium battery equipments.The processing of numerically-controlled machine tool at present Mode mainly has open loop, semiclosed loop and closed loop processing.Open loop processing is by worker's manual measurement and will not conform to after processing is completed Lattice product feedback is to technologist, adjusting process parameter;Semiclosed loop processing uses the parts feedback such as pulse coder on lathe The parameters such as motor speed control process;And closed loop processing mode is using cell feeds backs positions such as photoelectric sensor, limiters It sets, realizes closed-loop control.But above-mentioned processing method does not account for the processing cutting process of numerically-controlled machine tool, testing result has Time-lag effect causes the decline of processing efficiency, can not achieve the Precision Machining of real-time closed-loop control.
Summary of the invention
Aiming at the above defects or improvement requirements of the prior art, the closed loop control based on on-position measure that the present invention provides a kind of Precision machining method processed and system are added in real time it is intended that carrying out on-position measure by Image Acquisition and laser ranging Local critical size during work calculates mismachining tolerance and calculates processing compensation based on neural network algorithm real-time fitting Value, Automatic Optimal machining path realize the Precision Machining of real-time closed-loop control to reduce mismachining tolerance.
To achieve the goals above, according to one aspect of the present invention, it provides a kind of based on the closed loop control detected in place Precision machining method processed, includes the following steps:
S1, machine tool carry out time processing process according to machining path is preset;
After S2, completion step S1, or in step S1 implementation procedure in real time, the shape ruler of in-situ acquisition workpiece Very little, profile critical spot size and machined parameters, and neural network intelligent compensation model is inputted in real time, calculate the error of cutter Offset C and the machining path for optimizing next step accordingly carry out dynamic in real time with the processing to next step and compensate;Wherein:
Outer dimension, profile critical spot size and machined parameters include: the shape S, outer dimension H, workpiece material of workpiece Matter Mp, workpiece precise requirements A, cutter material Mt, machine tool chief axis speed Vm, tool feeding speed Vt, cutting fluid F, manufacturing procedure WsWith mismachining tolerance data;Mismachining tolerance data include the form error δ of workpieceSWith the appearance and size error delta of workpieceH, δSAnd δH It is the shape S, the measured value of appearance and size H and the difference of design value of workpiece respectively.
Neural network intelligent compensation model, be by using the outer dimension of finished work and profile critical spot size as Input, corresponding error compensation value C are trained to obtain as output to neural network
S3, using step S2 optimization after next step machining path be used as the default machining path of step S1, repeatedly step S1, S2 are until complete the process.
Further, it in step S2, presets workpiece surface and needs the key point that acquires, when measurement, clapped by camera According to workpiece configurations overall size is obtained as workpiece shapes S, the height dimension of workpiece surface key point is obtained by laser ranging As the corresponding appearance and size H of key point.
Further, in step S2, Laser Measuring is first carried out to workpiece surface corresponding position according to preset key point Away from finding out the height error of key point, then carry out data based on radial basis function and predict interpolation, generated according to preset key point More interpolation key points, then calculate the height error of interpolation key point, and by preset key point and interpolation key point Error delta of the height error as appearance and size HHCompensate calculating.
Further, intermediate that every i mm, one pass is set on machining path from start-stop point to ending point in step S2 Key point, presets N number of key point altogether, obtains the coordinate value x={ x of preset key point1,x2,…xi,…xN};It chooses radial Basic function are as follows:
The then interpolation expression of radial basis function are as follows:
Wherein, r=| x-xi|, it is coordinate x and coordinate value xiTwo norms;σ indicates the extension constant of radial basis function, instead The width of radial basis function image is answered, σ is smaller, and width is narrower, and function more has selectivity;c0For constant term, c1For first order Coefficient, λiFor corresponding to xiRadial basis functionCoefficient;
According to preset N number of key point and the appearance and size error of i-th of the key point measuredUse matrix SVD points Solution or least square method calculate the c in f (x)0、c1And λi, to obtain interpolation expression, and then find out on machining path The appearance and size error of other interpolation key points.
To achieve the goals above, the present invention also provides a kind of based on the closed-loop control Precision Machining system detected in place System, comprising: industrial camera, industrial personal computer, laser range finder and closed loop control process module;Wherein:
Industrial camera is used to carry out the preset key point of workpiece surface for shooting workpiece planarization image, laser range finder Laser ranging obtains its height;
Industrial personal computer is used to control the work of industrial camera and laser range finder, and closed loop control process module is called to carry out Error compensation;
Wherein, closed loop control process module executes examining as described in preceding any one based in place when being called by industrial personal computer The closed-loop control precision machining method of survey.
Further, industrial camera is equipped with optical lens and annular light source;Annular light source is by circularizing multiple photographs of arrangement Bright lamp composition;Each headlamp is distributed in around optical lens in a ring.
In general, the above technical scheme conceived by the present invention compared with prior art, can obtain following beneficial to effect Fruit:
(1) by machine tooling cutting process in view of passing through machine vision and Laser Measuring in size detection and closed-loop control Away from size detecting method, improve measuring system to the anti-interference ability of the external disturbances such as cutting fluid and chip.Also, shape Error directly by and its planar graph that obtains of vision calculate and obtained with the difference of design value, and pattern error is surveyed by laser ranging Operation efficiency can be equally greatly promoted compared to the method that traditional three-dimensional modeling calculates error away from acquisition, and then is promoted and is closed The real-time of ring control.
(2) scale error measurement is formed into closed loop in conjunction with Machine-Tool Control, with real-time control process, to machining deviation Compensation in time, improves processing efficiency and Seiko precision, and have certain open to the Precision Machining scene of other similar situation Send out meaning.
(3) method of the invention only needs the error of the several key points of actual measurement, and interpolation pass can be sought by interpolation method Key point position and then the error for obtaining interpolation key point, can be improved size detection speed, only need the error of several key points just Workpiece topography scale error can be calculated, detection efficiency is improved and can guarantee detection accuracy.
Detailed description of the invention
Fig. 1 is the schematic view of the mounting position of camera in the preferred embodiment of the present invention, camera lens and annular light source;
Fig. 2 is the floor map of annular light source in Fig. 1;
Fig. 3 is the machine vision flat shape dimensional measurement schematic diagram in the preferred embodiment of the present invention;
Fig. 4 is that laser measurement point of the present invention chooses schematic diagram;
Fig. 5 is that Interpolation Property of Radial Basis Function of the present invention calculates schematic diagram;
Fig. 6 is the conceptual scheme of detection and closed loop processing system in place of the present invention;
Fig. 7 is the flow diagram of the preferred embodiment of the present invention.
In all the appended drawings, identical appended drawing reference is used to denote the same element or structure, in which:
1- industrial camera, 2- optical lens, 3- annular light source, 4-LED lamp.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and It is not used in the restriction present invention.As long as in addition, technical characteristic involved in the various embodiments of the present invention described below Not constituting a conflict with each other can be combined with each other.
Present invention discloses a kind of closed loop processing control systems and method using on-position measure technology.Wherein measure part Industrial camera and light source arrangement as shown in Fig. 1, the accurate measurement point of laser measuring head is chosen as shown in Fig. 2.System Measurement part worked by control software control and read feedback image and measurement data, then with theoretical process comparing calculation Mismachining tolerance is controlled software using neural network model of mind and is calculated machine tool by interpolation algorithm densification appearance and size error Numerically-controlled machine tool is fed back to after tool compensation, machine tool is fed according to the processing of processing compensating approach next step.
The image acquisition part point working principle is that the annular light source installed on camera passes through light by control software systems Controller control in source issues the flash of light of predetermined luminance, and camera is taken pictures by software control simultaneously, and gained image transmitting to software passes through The technologies such as image preprocessing, image segmentation, edge fitting measure the critical size of workpiece, and mismachining tolerance is calculated.Due to Machine vision can simultaneously measure the entire all critical sizes for measuring part, and the interference to cutting fluid and chip It is insensitive, therefore all sizes of workpiece part can be rapidly and accurately measured, but monocular camera machine vision measurement component can not The depth information of workpiece is perceived, therefore height (depth) appearance and size mismachining tolerance of workpiece is measured using laser measuring head.Swash Light measurement head is worked at the same time with machine vision metrology component, and laser measuring head uses triangulation methods, and precise measurement workpiece is high The key point dimensioned error for spending (depth) pattern, as a result returns to control software, and software is calculated by Interpolation Property of Radial Basis Function Method calculates the mismachining tolerance of more key points in workpiece height (depth) pattern.Software unites to two above-mentioned mismachining tolerances One processing, calculates offset by neural network adjustment algorithm, compensation result needed for being converted into CNC system is finally controlled The servo-system of lathe processed is realized and is corrected to the machined parameters of lathe next step, to guarantee the accuracy of workpiece size.
System of the invention, method and concrete application are described in detail below with reference to a specific embodiment.
As shown in Figure 1, Figure 2, Figure 6 shows, the closed-loop control precision machining system based on on-position measure that the invention proposes a kind of, It uses the on-position measure tool of industrial camera and laser ranging head, the crucial ruler in the part of product in real-time measurement process It is very little, and cooperate related software system, by process and processing result size comparison, mismachining tolerance is calculated, and by mating Neural network algorithm the Fitting Calculation in software processes offset, and Automatic Optimal machining path, reduces mismachining tolerance.Wherein The working condition of industrial camera and measuring head is controlled by PLC controller, and carries out data exchange with corresponding software systems.
Specifically, the present embodiment, which uses, is based on machine vision and laser ranging head union measuring method, and which includes works The hardware facilities such as industry camera, industrial lens, annular light source, industrial personal computer, laser ranging head and other corresponding frock clamps.It is preferred that Ground, in the present embodiment:
The industrial camera be general industry camera, pixel resolution select with workpieces processing outer dimension for according to According in order to which rapidity and the accuracy etc. that meet measurement require, this system uses 2000W pixel CMOS camera;
The camera is equipped with ordinary optical camera lens, and focal length size need to meet workpiece size, using 8mm focal length fixed-focus mirror Head;
The light source is common annular light source, white light source is used in the present system, for shooting using industrial camera Illumination is provided when workpiece surface, brightness is controlled by the software kit system on industrial personal computer by light source controller.Annular light source It is arranged in the front of industrial lens, for following camera to acquire image.
The laser ranging head is technical grade laser range finder, is measured size using high-accuracy triangulation method, with reality Existing high-acruracy survey, measurement accuracy can reach 1 μm.
The machine vision metrology component is mainly used for measuring the local critical size of workpiece, at work, by industry control Software kit control light source flash of light and camera on machine are taken pictures, and obtain the photo of workpiece, and pass through ethernet line for image transmitting To control software, software carries out workpiece image by subpixel accuracies image processing methods such as centroid method and edge fittings Processing, measurement obtains measuring local critical size on workpiece, and compares with processing technology theoretical size, finds out processing and misses Difference transfers to the intelligent optimization algorithm in software to use.Image processing techniques of 20000000 pixel resolutions in subpixel accuracy Under, pixel computational accuracy can achieve micron order.
As shown in figure 3, the measurement of the machine vision is confined to two-dimensional surface, appearance profile size can only be measured, it can not The depth information of workpiece is measured, therefore makes up this defect using laser measuring head, the pattern that laser measuring head measures workpiece is high (depth) size is spent, corresponding error amount is calculated.
As shown in Figure 4, Figure 5, the laser ranging head is when measuring workpiece surface appearance, according to the preset pass of software Key point measures workpiece surface corresponding position, is carried out pair according to the machining path and workpiece size that pre-enter in software Than, crucial point tolerance is found out, the precise interpolation device based on radial basis function in software is reused and carries out data prediction interpolation, from And the error amount of more key points in workpiece surface appearance is calculated, and mended by software records and by intelligent algorithm in software Repay calculating.Due in process, the error amount on a machining path be it is inter-related, therefore, we do not need accurately The specific appearance and size of machining path is fitted, and only needs to find the relationship between mismachining tolerance.We are on processing road N number of key point is set on diameter, and from the start-stop point of machining path to ending point, centre is set as a sample point, i value every i mm Setting can according to processing situation set automatically, obtain the coordinate value x={ x of each key point1,x2,……xN(such as Fig. 4 In abscissa value).Choose polynomial basis function are as follows:
The then interpolation expression of radial basis function are as follows:
Wherein, r=| x-xi|, it is coordinate x and coordinate value xiTwo norms;σ indicates the extension constant of radial basis function, instead The width of radial basis function image is answered, σ is smaller, and width is narrower, and function more has selectivity;c0For constant term, c1For first order Coefficient, λiFor corresponding to xiRadial basis functionCoefficient;
According to preset N number of key point and the appearance and size error of i-th of the key point measuredUse matrix SVD points Solution or least square method calculate the c in f (x)0、c1And λi, to obtain interpolation expression, and then find out on machining path The appearance and size error of other interpolation key points.Size detection speed can be improved in this method, only needs the error of several key points Workpiece topography scale error can be calculated, detection efficiency is improved and guarantees detection accuracy.
The control software systems use intelligent compensation model algorithm neural network based, the mistake during machine tooling There are many poor influence factor, shape, outer dimension, workpiece material, workpiece precise requirements, machine spindle speed including workpiece, Tool feeding speed, process tool material, cutting fluid etc..The neural network algorithm, will be with based on industrial processes big data The process data accumulated into processing practice are subject to taxonomic revision, analyze the generation and processing of error in process Relationship between condition.The data that will acquire are with the shape S of workpiece, outer dimension H, workpiece material Mp, workpiece precise requirements A, cutter material Mt, machine tool chief axis speed Vm, tool feeding speed Vt, cutting fluid F, manufacturing procedure WsWith in these processing conditions As input data, the error compensation value C that technique expert is arranged in these process makees the mismachining tolerance data δ of lower generation For output.Establishing an output layer number of nodes is 9, and hidden layer number of nodes is 12, three layers of nerve net that output layer number of nodes is 1 Network.The process data of accumulation is trained using the gradient descent algorithm of SGD, obtains the neural network for predictive compensation value Model.
Control software uses the closed-loop control with control errors, will calculate resulting scale error above and pattern error is made For input data, lathe offset required for being calculated using trained neural network intelligent algorithm.Network model calculates Offset out drives the moving parts such as machine tool to compensate to the location of instruction and feeds through amplification control servo motor, and with slotting Complementary operation technology improves tool feeding compensation precision.
The sample frequency lower limit of the combined measurement system is machine vision part, and industrial camera maximum samples frame per second For 25FPS, the sample frequency of laser ranging head is up to thousands of times per second.The choosing of sample frequency and the profile critical point of measuring system Selecting is calculated by another neural network model in control software, according to the virtual condition of workpiece, processing request, machine The bed machined parameters such as the speed of mainshaft and tool feeding speed carry out calculating adjustment in real time, to guarantee the timeliness of measurement and accurate Property.
Workflow of the invention is illustrated below in conjunction with Fig. 7:
Preparation stage: workpiece for measurement is fixed on platen, is initialized to detection system;
Sizing calibration is carried out to machine vision measuring system information on the basis of workpiece for measurement surface, with worktable upper surface On the basis of laser measuring head is demarcated and is zeroed;
Process segment:
S1, numerically-controlled machine tool process workpiece for measurement according to scheduled processing route to after the completion of knife;
S2, error measure and compensation calculation:
For S21 when lathe is processed, control software carries out work according to preset sample frequency and sampling point position The measurement of part size;Include:
S211, control software transmission instruction make machine vision metrology component operation, and annular light source is sent out under control of the controller Preset flash of light out, industrial camera capture workpiece surface image are simultaneously transmitted to control software;
S212, control software quickly calculate workpiece external dimension according to the image of return, calculate error and record;Simultaneously Control laser measuring head work;
S213, laser measuring head measure the predetermined of workpiece height (depth) pattern under the sample frequency control of control software Since crucial spot size, measuring head processing starting point, measure along machining path according to the size interval (such as: 10mm) of setting Key point mismachining tolerance, and return result to control software;
S214, control software solve interpolation using Interpolation Property of Radial Basis Function algorithm according to height (depth) measurement error results Then expression formula selects more key points on machining path, 2 points of reselection in the spacing distance of key point before, Calculate more profile critical point tolerances.
Neural network model in S22, control software is input with these error amounts and processing conditions parameter, that is, input to Measure X=[S, H, Mp,A,Mt,Vm,Vt,F,Ws, δ], offset required for going out cutter according to neural network model intelligence computation is defeated Signal after conversion is fed back to numerically-controlled machine tool, is modified to the processing of next step by y=C out;
S3, numerically-controlled machine tool recycle above-described processing --- measurement process, until completing the processing of all process steps.
In other embodiments, the selection of the sample frequency of measuring system and profile critical point equally can be by control software Intelligent auto-control, can IT rank according to machining accuracy class requirement, machine spindle speed VmWith tool feeding speed Vt Equal machined parameters carry out calculating adjustment in real time, to guarantee the timeliness and accuracy of measurement.
In general, the present invention uses the on-position measure tool of industrial camera and laser ranging head, and real-time measurement is processed The local critical size of product in journey, and cooperate related software system, process and processing result size comparison calculate Mismachining tolerance, and offset is processed by the neural network algorithm the Fitting Calculation in software kit, and Automatic Optimal processes road Diameter reduces mismachining tolerance, has high control and machining accuracy, is particularly suitable for the precision of mold and lithium battery equipment industry Part process can be realized the complex-curved Precision Machining of kernel component.
As it will be easily appreciated by one skilled in the art that the foregoing is merely illustrative of the preferred embodiments of the present invention, not to The limitation present invention, any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should all include Within protection scope of the present invention.

Claims (6)

1. a kind of based on the closed-loop control precision machining method detected in place, which comprises the steps of:
S1, machine tool carry out time processing process according to machining path is preset;
After S2, completion step S1, or in step S1 implementation procedure in real time, outer dimension, the shape of in-situ acquisition workpiece Looks key spot size and machined parameters, and neural network intelligent compensation model is inputted in real time, calculate the error compensation of cutter Value C and the machining path for optimizing next step accordingly carry out dynamic in real time with the processing to next step and compensate;Wherein:
Outer dimension, profile critical spot size and machined parameters include: the shape S, outer dimension H, workpiece material M of workpiecep、 Workpiece precise requirements A, cutter material Mt, machine tool chief axis speed Vm, tool feeding speed Vt, cutting fluid F, manufacturing procedure WsWith Mismachining tolerance data;Mismachining tolerance data include the form error δ of workpieceSWith the appearance and size error delta of workpieceH, δSAnd δHRespectively It is the shape S, the measured value of appearance and size H and the difference of design value of workpiece;
Neural network intelligent compensation model is by using the outer dimension of finished work and profile critical spot size as defeated Enter, corresponding error compensation value C is trained to obtain as output to neural network;
S3, using step S2 optimization after next step machining path be used as the default machining path of step S1, repeatedly step S1, S2 Until completing the process.
2. as described in claim 1 a kind of based on the closed-loop control precision machining method detected in place, which is characterized in that step It in S2, presets workpiece surface and needs the key point that acquires, when measurement, taken pictures by camera and obtain workpiece configurations overall size As workpiece shapes S, the height dimension of workpiece surface key point is obtained as the corresponding pattern ruler of key point by laser ranging Very little H.
3. as claimed in claim 2 a kind of based on the closed-loop control precision machining method detected in place, which is characterized in that step In S2, laser ranging is first carried out to workpiece surface corresponding position according to preset key point, the height for finding out key point is missed Difference, then data are carried out based on radial basis function and predict interpolation, more interpolation key points are generated according to preset key point, then The height error of interpolation key point is calculated, and using the height error of preset key point and interpolation key point as appearance and size H Error deltaHCompensate calculating.
4. as claimed in claim 3 a kind of based on the closed-loop control precision machining method detected in place, which is characterized in that step It is intermediate that every imm, one key point is set on machining path from start-stop point to ending point in S2, N number of key is preset altogether Point obtains the coordinate value x={ x of preset key point1,x2,…xi,…xN};Choose radial basis function are as follows:
The then interpolation expression of radial basis function are as follows:
Wherein, r=| x-xi|, it is coordinate x and coordinate value xiTwo norms;σ indicates the extension constant of radial basis function, reaction The width of radial basis function image, σ is smaller, and width is narrower, and function more has selectivity;c0For constant term, c1For a term system Number, λiFor corresponding to xiRadial basis functionCoefficient;
According to preset N number of key point and the appearance and size error of i-th of the key point measuredDecomposed using matrix SVD or Person's least square method calculates the c in f (x)0、c1And λi, to obtain interpolation expression, and then find out on machining path other The appearance and size error of interpolation key point.
5. a kind of based on the closed-loop control precision machining system detected in place characterized by comprising industrial camera, industrial personal computer, Laser range finder and closed loop control process module;Wherein:
Industrial camera is used to carry out laser to the preset key point of workpiece surface for shooting workpiece planarization image, laser range finder Ranging obtains its height;
Industrial personal computer is used to control the work of industrial camera and laser range finder, and closed loop control process module is called to carry out error Compensation;
Wherein, closed loop control process module executed when being called by industrial personal computer as described in Claims 1 to 4 any one based on The closed-loop control precision machining method detected in place.
6. as claimed in claim 5 a kind of based on the closed-loop control precision machining system detected in place, which is characterized in that industry Camera is equipped with optical lens and annular light source;Annular light source by circularize multiple lighting lamp groups of arrangement at;Each headlamp is in ring Shape is distributed in around optical lens.
CN201910646784.8A 2019-07-17 2019-07-17 Closed-loop control precision machining method and system based on in-situ detection Active CN110376963B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910646784.8A CN110376963B (en) 2019-07-17 2019-07-17 Closed-loop control precision machining method and system based on in-situ detection

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910646784.8A CN110376963B (en) 2019-07-17 2019-07-17 Closed-loop control precision machining method and system based on in-situ detection

Publications (2)

Publication Number Publication Date
CN110376963A true CN110376963A (en) 2019-10-25
CN110376963B CN110376963B (en) 2020-12-08

Family

ID=68253863

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910646784.8A Active CN110376963B (en) 2019-07-17 2019-07-17 Closed-loop control precision machining method and system based on in-situ detection

Country Status (1)

Country Link
CN (1) CN110376963B (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110989494A (en) * 2019-11-29 2020-04-10 上海交通大学 Thin-wall part machining error measuring and compensating method based on trigger type measuring head
CN112059726A (en) * 2020-08-31 2020-12-11 西安精雕精密机械工程有限公司 On-machine measurement and compensation processing method of workpiece with multiple reference characteristics
CN112198838A (en) * 2020-10-12 2021-01-08 湖南汽车工程职业学院 Intelligent detection system for working condition parameters of machine tool
CN112255964A (en) * 2020-10-12 2021-01-22 湖南汽车工程职业学院 Machine tool machining cutter remote temperature control system based on big data
CN112859742A (en) * 2021-01-12 2021-05-28 广州盛硕科技有限公司 Numerical control machine tool control system based on visual identification
CN113093648A (en) * 2021-03-31 2021-07-09 西门子(中国)有限公司 Automatic machining system and method for motor base
CN113304971A (en) * 2021-04-26 2021-08-27 深圳市世宗自动化设备有限公司 3D dynamic guiding dispensing compensation method, device and equipment and storage medium thereof
WO2021174900A1 (en) * 2020-03-02 2021-09-10 珠海格力智能装备有限公司 Machine tool precision analysis method and apparatus, precision measurer, and machine tool machining method
CN115933534A (en) * 2023-02-09 2023-04-07 山东山科世鑫科技有限公司 Numerical control intelligent detection system and method based on Internet of things
CN117260379A (en) * 2023-11-21 2023-12-22 靖江市恒友汽车部件制造有限公司 On-line control method for machining diameter of automobile part

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102773524A (en) * 2012-08-01 2012-11-14 西北工业大学 Hole making method with alignment based on machine vision
CN104933220A (en) * 2015-05-11 2015-09-23 东莞市凌英模具塑胶有限公司 High precision manufacturing method and injection mold for plastic injection mold for complex curved surface
CN106584209A (en) * 2016-11-10 2017-04-26 哈尔滨理工大学 Real-time online monitoring method for tool wear based on cloud manufacturing
CN107132814A (en) * 2017-02-24 2017-09-05 上海交通大学 Digital control system in open type based on machine vision condition monitoring and error compensation

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102773524A (en) * 2012-08-01 2012-11-14 西北工业大学 Hole making method with alignment based on machine vision
CN104933220A (en) * 2015-05-11 2015-09-23 东莞市凌英模具塑胶有限公司 High precision manufacturing method and injection mold for plastic injection mold for complex curved surface
CN106584209A (en) * 2016-11-10 2017-04-26 哈尔滨理工大学 Real-time online monitoring method for tool wear based on cloud manufacturing
CN107132814A (en) * 2017-02-24 2017-09-05 上海交通大学 Digital control system in open type based on machine vision condition monitoring and error compensation

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
杨丁 等: "基于机器视觉的注射模具型腔异常检测", 《工程塑料应用》 *

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110989494A (en) * 2019-11-29 2020-04-10 上海交通大学 Thin-wall part machining error measuring and compensating method based on trigger type measuring head
WO2021174900A1 (en) * 2020-03-02 2021-09-10 珠海格力智能装备有限公司 Machine tool precision analysis method and apparatus, precision measurer, and machine tool machining method
CN112059726A (en) * 2020-08-31 2020-12-11 西安精雕精密机械工程有限公司 On-machine measurement and compensation processing method of workpiece with multiple reference characteristics
CN112198838A (en) * 2020-10-12 2021-01-08 湖南汽车工程职业学院 Intelligent detection system for working condition parameters of machine tool
CN112255964A (en) * 2020-10-12 2021-01-22 湖南汽车工程职业学院 Machine tool machining cutter remote temperature control system based on big data
CN112859742B (en) * 2021-01-12 2021-08-06 广州盛硕科技有限公司 Numerical control machine tool control system based on visual identification
CN112859742A (en) * 2021-01-12 2021-05-28 广州盛硕科技有限公司 Numerical control machine tool control system based on visual identification
CN113093648A (en) * 2021-03-31 2021-07-09 西门子(中国)有限公司 Automatic machining system and method for motor base
CN113304971A (en) * 2021-04-26 2021-08-27 深圳市世宗自动化设备有限公司 3D dynamic guiding dispensing compensation method, device and equipment and storage medium thereof
CN113304971B (en) * 2021-04-26 2022-12-13 深圳市世宗自动化设备有限公司 3D dynamic guiding dispensing compensation method, device and equipment and storage medium thereof
CN115933534A (en) * 2023-02-09 2023-04-07 山东山科世鑫科技有限公司 Numerical control intelligent detection system and method based on Internet of things
CN115933534B (en) * 2023-02-09 2023-11-07 山东山科世鑫科技有限公司 Numerical control intelligent detection system and method based on Internet of things
CN117260379A (en) * 2023-11-21 2023-12-22 靖江市恒友汽车部件制造有限公司 On-line control method for machining diameter of automobile part
CN117260379B (en) * 2023-11-21 2024-02-23 靖江市恒友汽车部件制造有限公司 On-line control method for machining diameter of automobile part

Also Published As

Publication number Publication date
CN110376963B (en) 2020-12-08

Similar Documents

Publication Publication Date Title
CN110376963A (en) It is a kind of based on the closed-loop control precision machining method detected in place and system
CN109489580B (en) On-machine point cloud detection and compensation method for surface processing of aero-engine blade
US10189133B2 (en) Measurement, calibration and compensation system and method for machine tool
CN108332946B (en) A kind of reflection focal length in microlens array mold turnery processing is in position detecting method
CN106841206B (en) Untouched online inspection method is cut in heavy parts chemical milling
CN106863014B (en) A kind of five-axle number control machine tool linear axis geometric error detection method
CN107270833A (en) A kind of complex curved surface parts three-dimension measuring system and method
CN103433810B (en) Complicated curve surface normal vector on-machine detection device and method
Takaya In-process and on-machine measurement of machining accuracy for process and product quality management: A review
CN103801989B (en) A kind of airborne automatic measurement system of determining workpiece coordinate initial point of processing based on image
CN105643092A (en) Method for regaining coordinates of workpiece through CCD during combined machining
CN101000499A (en) Contour machining method and system based on multi-sensor integral measuring
CN108527007B (en) Vertical machining center on-machine measuring system and method based on optical triangulation method
CN103354770A (en) Laser processing method and laser processing device
CN108127206B (en) Laser brazing process transplanting method and laser brazing device capable of transplanting data
CN208780144U (en) A kind of online vision detection system of connecting hole
CN108917600A (en) A kind of labyrinth blank processing positioning method based on three-dimensional reverse
CN105841641A (en) Laser triangulation method-based three-dimensional measuring instrument and flatness detection method
CN109341532A (en) A kind of part coordinate scaling method based on structure feature towards automatic assembling
CN105354360B (en) Large Aircraft Components assembly interface finishes measurement of coordinates and controls net closed loop method for building up
CN107270820A (en) A kind of large thin-walled component wall thickness on-position measure system and method
CN107932185A (en) The numerically-controlled machine tool closed loop system of view-based access control model
CN113070644A (en) Microstructure array composite processing method
CN105716547A (en) Rapid measurement device and method for planeness of mechanical workpiece
CN111985149A (en) Convolutional network-based five-axis machine tool rotating shaft thermal error modeling method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right

Effective date of registration: 20220104

Address after: 430000 No. 07 (b452), floor 3, building 3, phase III, international enterprise center, No. 1, Guanggu Avenue, Donghu New Technology Development Zone, Wuhan, Hubei (Wuhan area of free trade zone)

Patentee after: Wuhan moding Technology Co.,Ltd.

Address before: 430074 Hubei Province, Wuhan city Hongshan District Luoyu Road No. 1037

Patentee before: HUAZHONG University OF SCIENCE AND TECHNOLOGY

TR01 Transfer of patent right